 Georgi Gerganov
|
57dd55e2c7
server : fix kv cache management (#3588)
|
há 2 anos atrás |
 Michael Coppola
|
a8bdd65525
server : add parameter -tb N, --threads-batch N (#3584)
|
há 2 anos atrás |
 Kerfuffle
|
70c29da118
common : fix mirostat state when using multiple sequences (#3543)
|
há 2 anos atrás |
 vvhg1
|
11ea5c7d96
infill. : fix tokenization (#3508)
|
há 2 anos atrás |
 Jhen-Jie Hong
|
97af49fa39
server : reuse llama_sample_token common util (#3494)
|
há 2 anos atrás |
 Kenvix ⭐
|
45eba9369f
build : use std::make_tuple() for compatibility with older GCC versions (#3488)
|
há 2 anos atrás |
|
Jhen-Jie Hong
|
e8b8d32e86
server : fix incorrect num_tokens_predicted (#3480)
|
há 2 anos atrás |
|
Georgi Gerganov
|
ac2219fef3
llama : fix session saving/loading (#3400)
|
há 2 anos atrás |
|
vvhg1
|
c97f01c362
infill : add new example + extend server API (#3296)
|
há 2 anos atrás |
 slaren
|
16bc66d947
llama.cpp : split llama_context_params into model and context params (#3301)
|
há 2 anos atrás |
 xaedes
|
0e76a8992c
train : finetune LORA (#2632)
|
há 2 anos atrás |
|
Georgi Gerganov
|
ec893798b7
llama : custom attention mask + parallel decoding + no context swaps (#3228)
|
há 2 anos atrás |
 Cebtenzzre
|
a5661d7e71
llama : allow gguf RoPE keys to be overridden with defaults (#3240)
|
há 2 anos atrás |
|
Cebtenzzre
|
3aefaab9e5
check C++ code with -Wmissing-declarations (#3184)
|
há 2 anos atrás |
|
Cebtenzzre
|
00d62adb79
fix some warnings from gcc and clang-tidy (#3038)
|
há 2 anos atrás |
|
Cebtenzzre
|
de2fe892af
examples : replace fprintf to stdout with printf (#3017)
|
há 2 anos atrás |
|
Jhen-Jie Hong
|
571083f508
server : avoid aniprompt in probabilities of final response (#2849)
|
há 2 anos atrás |
|
Cebtenzzre
|
ef15649972
build : fix most gcc and clang warnings (#2861)
|
há 2 anos atrás |
 Johannes Gäßler
|
6b73ef1201
YAML result logging + preset script (#2657)
|
há 2 anos atrás |
|
Georgi Gerganov
|
edd4c14817
llama : more tokenizer fixes (#2810)
|
há 2 anos atrás |
 Bruce MacDonald
|
c1ac54b77a
server : add `/detokenize` endpoint (#2802)
|
há 2 anos atrás |
 Matt Pulver
|
c82742ac9c
llama : add llama_beam_search() (#2267)
|
há 2 anos atrás |
|
Jhen-Jie Hong
|
29674ab4e8
server : display token probabilities in the UI (#2489)
|
há 2 anos atrás |
 Xiao-Yong Jin
|
b8ad1b66b2
server : allow json array in prompt or content for direct token input (#2306)
|
há 2 anos atrás |
|
Johannes Gäßler
|
c63bb1d16a
CUDA: use mul_mat_q kernels by default (#2683)
|
há 2 anos atrás |
|
Jhen-Jie Hong
|
226255b44e
server : fallback to default if client param is null (#2688)
|
há 2 anos atrás |
|
Georgi Gerganov
|
6381d4e110
gguf : new file format with flexible meta data (beta) (#2398)
|
há 2 anos atrás |
|
Jhen-Jie Hong
|
3ebb00935f
server : add missing /json-schema-to-grammar.mjs (#2616)
|
há 2 anos atrás |
 Cheng Shao
|
d75561df20
server : add --numa support (#2524)
|
há 2 anos atrás |
 Equim
|
53dc399472
server: fixed wrong variable name in timing json (#2579)
|
há 2 anos atrás |
